← Back to Publications List

IoT-Enabled Digital Twin Ecosystem for Optimizing Maintenance and Minimizing Downtime in Smart Manufacturing

Students & Supervisors

Student Authors
Syeda Shakira Akter
Md. Maruf Hossain Munna
Bachelor of Science in Computer Science & Engineering, FST
Khondaker Iffti Hasan Turjo
Bachelor of Science in Computer Science & Engineering, FST
Md. Asif Sarker Emon
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Md. Faruk Abdullah Al Sohan
Lecturer, Faculty, FST

Abstract

In the fiercely competitive landscape of the manufacturing sector, reducing downtime and enhancing maintenance efficiency are essential for sustained operational success. This research presents an IoT-enabled digital twin ecosystem designed to improve maintenance scheduling and minimize downtime in complex smart manufacturing environments. The proposed model seamlessly integrates IoT sensors, digital twin technology, and predictive analytics, leveraging Long Short-Term Memory (LSTM) models to create virtual replicas of physical assets and workflows. This integration facilitates real-time monitoring and predictive maintenance sensors continuously gathering critical data on various parameters, such as temperature, vibration, pressure, and energy consumption. This data is processed using both edge and cloud computing, and subsequently incorporated into the digital twin model, which reflects the real-time operational status and health of the physical assets. The predictive analytics, driven by LSTM models, analyze historical data trends to forecast potential failures, allowing for timely maintenance interventions that prevent disruptions and extend the lifespan of assets. To ensure the protection of sensitive information and maintain operational integrity, robust security measures—including data encryption and anomaly detection—are implemented. By automating maintenance schedules, minimizing unexpected downtimes, and enhancing resource efficiency, this ecosystem fosters a resilient and highly optimized manufacturing process., and improving resource efficiency, this ecosystem delivers a resilient and highly optimized manufacturing process

Keywords

Smart Manufacturing Digital Twin Real-Time Data LSTM Ecosystem

Publication Details

  • DOI: 10.46254/BA07.20240144
  • Type of Publication: Conference 
  • Conference Name: 7th IEOM Bangladesh International Conference on Industrial Engineering and Operations Management
  • Date of Conference: 21/12/2024 - 21/12/2024
  • Venue: 7th IEOM Bangladesh International Conference on Industrial Engineering and Operations Management
  • Organizer: IEOM Society International
View on Publisher